Machine learning applications in cell image analysis

High-quality AFM image acquisition of living cells by modified residual encoder-decoder network

Atomic force microscope enables ultra-precision imaging of living cells. However, atomic force microscope imaging is a complex and time-consuming process. The obtained images of living cells usually have low resolution and are easily influenced by noise leading to unsatisfactory imaging quality, obstructing the research and analysis based on cell images. Herein, an adaptive attention image reconstruction network based on residual encoder-decoder was proposed, through the combination of deep learning technology and atomic force microscope imaging supporting high-quality cell image acquisition. Compared with other learning-based methods, the proposed network showed higher peak signal-to-noise ratio, higher structural similarity and better image reconstruction performances. In addition, the cell images reconstructed by each method were used for cell recognition, and the cell images reconstructed by the proposed network had the highest cell recognition rate. The proposed network has brought insights into the atomic force microscope-based imaging of living cells and cell image reconstruction, which is of great significance in biological and medical research.

From pixels to connections: exploring in vitro neuron reconstruction software for network graph generation

Digital reconstruction has been instrumental in deciphering how in vitro neuron architecture shapes information flow. Emerging approaches reconstruct neural systems as networks with the aim of understanding their organization through graph theory. Computational tools dedicated to this objective build models of nodes and edges based on key cellular features such as somata, axons, and dendrites. Fully automatic implementations of these tools are readily available, but they may also be purpose-built from specialized algorithms in the form of multi-step pipelines. Here we review software tools informing the construction of network models, spanning from noise reduction and segmentation to full network reconstruction. The scope and core specifications of each tool are explicitly defined to assist bench scientists in selecting the most suitable option for their microscopy dataset. Existing tools provide a foundation for complete network reconstruction, however more progress is needed in establishing morphological bases for directed/weighted connectivity and in software validation.

Advances in the study of tertiary lymphoid structures in the immunotherapy of breast cancer

Breast cancer, as one of the most common malignancies in women, exhibits complex and heterogeneous pathological characteristics across different subtypes. Triple-negative breast cancer (TNBC) and HER2-positive breast cancer are two common and highly invasive subtypes within breast cancer. The stability of the breast microbiota is closely intertwined with the immune environment, and immunotherapy is a common approach for treating breast cancer.Tertiary lymphoid structures (TLSs), recently discovered immune cell aggregates surrounding breast cancer, resemble secondary lymphoid organs (SLOs) and are associated with the prognosis and survival of some breast cancer patients, offering new avenues for immunotherapy. Machine learning, as a form of artificial intelligence, has increasingly been used for detecting biomarkers and constructing tumor prognosis models. This article systematically reviews the latest research progress on TLSs in breast cancer and the application of machine learning in the detection of TLSs and the study of breast cancer prognosis. The insights provided contribute valuable perspectives for further exploring the biological differences among different subtypes of breast cancer and formulating personalized treatment strategies.

An integrative machine learning model for the identification of tumor T-cell antigens

The escalating global incidence of cancer poses significant health challenges, underscoring the need for innovative and more efficacious treatments. Cancer immunotherapy, a promising approach leveraging the body's immune system against cancer, emerges as a compelling solution. Consequently, the identification and characterization of tumor T-cell antigens (TTCAs) have become pivotal for exploration. In this manuscript, we introduce TTCA-IF, an integrative machine learning-based framework designed for TTCAs identification. TTCA-IF employs ten feature encoding types in conjunction with five conventional machine learning classifiers. To establish a robust foundation, these classifiers are trained, resulting in the creation of 150 baseline models. The outputs from these baseline models are then fed back into the five classifiers, generating their respective meta-models. Through an ensemble approach, the five meta-models are seamlessly integrated to yield the final predictive model, the TTCA-IF model. Our proposed model, TTCA-IF, surpasses both baseline models and existing predictors in performance. In a comparative analysis involving nine novel peptide sequences, TTCA-IF demonstrated exceptional accuracy by correctly identifying 8 out of 9 peptides as TTCAs. As a tool for screening and pinpointing potential TTCAs, we anticipate TTCA-IF to be invaluable in advancing cancer immunotherapy.

Uncovering hidden treasures: Mapping morphological changes in the differentiation of human mesenchymal stem cells to osteoblasts using deep learning

Deep Learning (DL) is becoming an increasingly popular technology being employed in life sciences research due to its ability to perform complex and time-consuming tasks with significantly greater speed, accuracy, and reproducibility than human researchers - allowing them to dedicate their time to more complex tasks. One potential application of DL is to analyze cell images taken by microscopes. Quantitative analysis of cell microscopy images remain a challenge - with manual cell characterization requiring excessive amounts of time and effort. DL can address these issues, by quickly extracting such data and enabling rigorous, empirical analysis of images. Here, DL is used to quantitively analyze images of Mesenchymal Stem Cells (MSCs) differentiating into Osteoblasts (OBs), tracking morphological changes throughout this transition. The changes in morphology throughout the differentiation protocol provide evidence for a distinct path of morphological transformations that the cells undergo in their transition, with changes in perimeter being observable before changes in eceentricity. Subsequent differentiation experiments can be quantitatively compared with our dataset to concretely evaluate how different conditions affect differentiation and this paper can also be used as a guide for researchers on how to utilize DL workflows in their own labs.

Machine learning algorithms for FPGA Implementation in biomedical engineering applications: A review

Field Programmable Gate Arrays (FPGAs) are integrated circuits that can be configured by the user after manufacturing, making them suitable for customized hardware prototypes, a feature not available in general-purpose processors in Application Specific Integrated Circuits (ASIC). In this paper, we review the vast Machine Learning (ML) algorithms implemented on FPGAs to increase performance and capabilities in healthcare technology over 2001-2023. In particular, we focus on real-time ML algorithms targeted to FPGAs and hybrid System-on-a-chip (SoC) FPGA architectures for biomedical applications. We discuss how previous works have customized and optimized their ML algorithm and FPGA designs to address the putative embedded systems challenges of limited memory, hardware, and power resources while maintaining scalability to accommodate different network sizes and topologies. We provide a synthesis of articles implementing classifiers and regression algorithms, as they are significant algorithms that cover a wide range of ML algorithms used for biomedical applications. This article is written to inform the biomedical engineering and FPGA design communities to advance knowledge of FPGA-enabled ML accelerators for biomedical applications.

AI models for automated segmentation of engineered polycystic kidney tubules

Autosomal dominant polycystic kidney disease (ADPKD) is a monogenic, rare disease, characterized by the formation of multiple cysts that grow out of the renal tubules. Despite intensive attempts to develop new drugs or repurpose existing ones, there is currently no definitive cure for ADPKD. This is primarily due to the complex and variable pathogenesis of the disease and the lack of models that can faithfully reproduce the human phenotype. Therefore, the development of models that allow automated detection of cysts' growth directly on human kidney tissue is a crucial step in the search for efficient therapeutic solutions. Artificial Intelligence methods, and deep learning algorithms in particular, can provide powerful and effective solutions to such tasks, and indeed various architectures have been proposed in the literature in recent years. Here, we comparatively review state-of-the-art deep learning segmentation models, using as a testbed a set of sequential RGB immunofluorescence images from 4 in vitro experiments with 32 engineered polycystic kidney tubules. To gain a deeper understanding of the detection process, we implemented both pixel-wise and cyst-wise performance metrics to evaluate the algorithms. Overall, two models stand out as the best performing, namely UNet++ and UACANet: the latter uses a self-attention mechanism introducing some explainability aspects that can be further exploited in future developments, thus making it the most promising algorithm to build upon towards a more refined cyst-detection platform. UACANet model achieves a cyst-wise Intersection over Union of 0.83, 0.91 for Recall, and 0.92 for Precision when applied to detect large-size cysts. On all-size cysts, UACANet averages at 0.624 pixel-wise Intersection over Union. The code to reproduce all results is freely available in a public GitHub repository.

Quantifying cytoskeletal organization from optical microscopy data

The actin cytoskeleton plays a pivotal role in a broad range of physiological processes including directing cell shape and subcellular organization, determining cell mechanical properties, and sensing and transducing mechanical forces. The versatility of the actin cytoskeleton arises from the ability of actin filaments to assemble into higher order structures through their interaction with a vast set of regulatory proteins. Actin filaments assemble into bundles, meshes, and networks, where different combinations of these structures fulfill specific functional roles. Analyzing the organization and abundance of different actin structures from optical microscopy data provides a valuable metric for assessing cell physiological function and changes associated with disease. However, quantitative measurements of the size, abundance, orientation, and distribution of different types of actin structure remains challenging both from an experimental and image analysis perspective. In this review, we summarize image analysis methods for extracting quantitative values that can be used for characterizing the organization of actin structures and provide selected examples. We summarize the potential sample types and metric reported with different approaches as a guide for selecting an image analysis strategy.

Advanced optical imaging for the rational design of nanomedicines

Despite the enormous potential of nanomedicines to shape the future of medicine, their clinical translation remains suboptimal. Translational challenges are present in every step of the development pipeline, from a lack of understanding of patient heterogeneity to insufficient insights on nanoparticle properties and their impact on material-cell interactions. Here, we discuss how the adoption of advanced optical microscopy techniques, such as super-resolution optical microscopies, correlative techniques, and high-content modalities, could aid the rational design of nanocarriers, by characterizing the cell, the nanomaterial, and their interaction with unprecedented spatial and/or temporal detail. In this nanomedicine arena, we will discuss how the implementation of these techniques, with their versatility and specificity, can yield high volumes of multi-parametric data; and how machine learning can aid the rapid advances in microscopy: from image acquisition to data interpretation.

ModelRevelator: Fast phylogenetic model estimation via deep learning

Selecting the best model of sequence evolution for a multiple-sequence-alignment (MSA) constitutes the first step of phylogenetic tree reconstruction. Common approaches for inferring nucleotide models typically apply maximum likelihood (ML) methods, with discrimination between models determined by one of several information criteria. This requires tree reconstruction and optimisation which can be computationally expensive. We demonstrate that neural networks can be used to perform model selection, without the need to reconstruct trees, optimise parameters, or calculate likelihoods. We introduce ModelRevelator, a model selection tool underpinned by two deep neural networks. The first neural network, NNmodelfind, recommends one of six commonly used models of sequence evolution, ranging in complexity from Jukes and Cantor to General Time Reversible. The second, NNalphafind, recommends whether or not a Γ-distributed rate heterogeneous model should be incorporated, and if so, provides an estimate of the shape parameter, ɑ. Users can simply input an MSA into ModelRevelator, and swiftly receive output recommending the evolutionary model, inclusive of the presence or absence of rate heterogeneity, and an estimate of ɑ. We show that ModelRevelator performs comparably with likelihood-based methods and the recently published machine learning method ModelTeller over a wide range of parameter settings, with significant potential savings in computational effort. Further, we show that this performance is not restricted to the alignments on which the networks were trained, but is maintained even on unseen empirical data. We expect that ModelRevelator will provide a valuable alternative for phylogeneticists, especially where traditional methods of model selection are computationally prohibitive.

The determination of optimum segmentation parameters using genetic algorithms: Application to different segmentation algorithms and transmission electron microscopy tomography reconstructed volumes

A method for optimizing an automatic selection of values for parameters that feed segmentation algorithms is proposed. Evolutionary optimization techniques in combination with a fitness function based on a mutual information parameter have been used to find the optimal parameter values of region growing, fuzzy c-means and graph cut segmentation algorithms. To validate the method, the segmentation of two transmission electron microscopy tomography reconstructed volumes of a carbon black-reinforced rubber and a polylactic acid and clay nanocomposite is carried out (i) using evolutionary optimization techniques and (ii) manually by experts. The results confirm that the use of evolutionary optimization techniques, such as genetic algorithms, reduces the computational operation cost needed for a total grid search of segmentation parameters, reducing the probability of reaching a false optimum, and improving the segmentation quality. HIGHLIGHTS: A new approach to optimize 3D segmentation algorithms. Methodology to optimize segmentation parameters and improve segmentation quality. Improvement on the results when using region growing, fuzzy c-means and graph cuts algorithms.

Generative models of morphogenesis in developmental biology

Understanding the mechanism by which cells coordinate their differentiation and migration is critical to our understanding of many fundamental processes such as wound healing, disease progression, and developmental biology. Mathematical models have been an essential tool for testing and developing our understanding, such as models of cells as soft spherical particles, reaction-diffusion systems that couple cell movement to environmental factors, and multi-scale multi-physics simulations that combine bottom-up rule-based models with continuum laws. However, mathematical models can often be loosely related to data or have so many parameters that model behaviour is weakly constrained. Recent methods in machine learning introduce new means by which models can be derived and deployed. In this review, we discuss examples of mathematical models of aspects of developmental biology, such as cell migration, and how these models can be combined with these recent machine learning methods.

Scaling up cell-counting efforts in neuroscience through semi-automated methods

Quantifying how the cellular composition of brain regions vary across development, aging, sex, and disease, is crucial in experimental neuroscience, and the accuracy of different counting methods is continuously debated. Due to the tedious nature of most counting procedures, studies are often restricted to one or a few brain regions. Recently, there have been considerable methodological advances in combining semi-automated feature extraction with brain atlases for cell quantification. Such methods hold great promise for scaling up cell-counting efforts. However, little focus has been paid to how these methods should be implemented and reported to support reproducibility. Here, we provide an overview of practices for conducting and reporting cell counting in mouse and rat brains, showing that critical details for interpretation are typically lacking. We go on to discuss how novel methods may increase efficiency and reproducibility of cell counting studies. Lastly, we provide practical recommendations for researchers planning cell counting.

A weak-labelling and deep learning approach for in-focus object segmentation in 3D widefield microscopy

Three-dimensional information is crucial to our understanding of biological phenomena. The vast majority of biological microscopy specimens are inherently three-dimensional. However, conventional light microscopy is largely geared towards 2D images, while 3D microscopy and image reconstruction remain feasible only with specialised equipment and techniques. Inspired by the working principles of one such technique-confocal microscopy, we propose a novel approach to 3D widefield microscopy reconstruction through semantic segmentation of in-focus and out-of-focus pixels. For this, we explore a number of rule-based algorithms commonly used for software-based autofocusing and apply them to a dataset of widefield focal stacks. We propose a computation scheme allowing the calculation of lateral focus score maps of the slices of each stack using these algorithms. Furthermore, we identify algorithms preferable for obtaining such maps. Finally, to ensure the practicality of our approach, we propose a surrogate model based on a deep neural network, capable of segmenting in-focus pixels from the out-of-focus background in a fast and reliable fashion. The deep-neural-network-based approach allows a major speedup for data processing making it usable for online data processing.

AMLnet, A deep-learning pipeline for the differential diagnosis of acute myeloid leukemia from bone marrow smears

Acute myeloid leukemia (AML) is a deadly hematological malignancy. Cellular morphology detection of bone marrow smears based on the French-American-British (FAB) classification system remains an essential criterion in the diagnosis of hematological malignancies. However, the diagnosis and discrimination of distinct FAB subtypes of AML obtained from bone marrow smear images are tedious and time-consuming. In addition, there is considerable variation within and among pathologists, particularly in rural areas, where pathologists may not have relevant expertise. Here, we established a comprehensive database encompassing 8245 bone marrow smear images from 651 patients based on a retrospective dual-center study between 2010 and 2021 for the purpose of training and testing. Furthermore, we developed AMLnet, a deep-learning pipeline based on bone marrow smear images, that can discriminate not only between AML patients and healthy individuals but also accurately identify various AML subtypes. AMLnet achieved an AUC of 0.885 at the image level and 0.921 at the patient level in distinguishing nine AML subtypes on the test dataset. Furthermore, AMLnet outperformed junior human experts and was comparable to senior experts on the test dataset at the patient level. Finally, we provided an interactive demo website to visualize the saliency maps and the results of AMLnet for aiding pathologists' diagnosis. Collectively, AMLnet has the potential to serve as a fast prescreening and decision support tool for cytomorphological pathologists, especially in areas where pathologists are overburdened by medical demands as well as in rural areas where medical resources are scarce.

Particle-based model shows complex rearrangement of tissue mechanical properties are needed for roots to grow in hard soil

When exposed to increased mechanical resistance from the soil, plant roots display non-linear growth responses that cannot be solely explained by mechanical principles. Here, we aim to investigate how changes in tissue mechanical properties are biologically regulated in response to soil strength. A particle-based model was developed to solve root-soil mechanical interactions at the cellular scale, and a detailed numerical study explored factors that affect root responses to soil resistance. Results showed how softening of root tissues at the tip may contribute to root responses to soil impedance, a mechanism likely linked to soil cavity expansion. The model also predicted the shortening and decreased anisotropy of the zone where growth occurs, which may improve the mechanical stability of the root against axial forces. The study demonstrates the potential of advanced modeling tools to help identify traits that confer plant resistance to abiotic stress.

m6 A mRNA methylation in human brain is disrupted in Lewy body disorders

AIMS

N⁶ -methyladenosine modification of RNA (m⁶ A) regulates translational control, which may influence neuronal dysfunction underlying neurodegenerative diseases.

METHODS

Using microscopy and a machine learning approach, we performed cellular profiling of m⁶ A-RNA abundance and YTHDF1/YTHDF3 m⁶ A reader expression within four regions of the human brain from non-affected individuals and individuals with Parkinson's disease, dementia with Lewy bodies or mild cognitive impairment (MCI).

RESULTS

In non-diseased tissue, we found that m⁶ A-modified RNAs showed cell-type and sub-compartment-specific variation. YTHDF1 and YTHDF3 showed opposing expression patterns in the cerebellum and the frontal and cingulate cortices. Machine learning quantitative image analysis revealed that m⁶ A-modified transcripts were significantly altered in localisation and abundance in disease tissue with significant decreases in m⁶ A-RNAs in Parkinson's disease, and significant increases in m⁶ A-RNA abundance in dementia with Lewy bodies. MCI tissue showed variability across regions but similar to DLB; in brain areas with an overall significant increase in m⁶ A-RNAs, modified RNAs within dendritic processes were reduced. Using mass spectrometry proteomic datasets to corroborate our findings, we found significant changes in YTHDF3 and m⁶ A anti-reader protein abundance in Alzheimer's disease (AD) and asymptomatic AD/MCI tissue and correlation with cognitive resilience.

CONCLUSIONS

These results provide evidence for disrupted m⁶ A regulation in Lewy body diseases and a plausible mechanism through which RNA processing could contribute to the formation of Lewy bodies and other dementia-associated pathological aggregates. The findings suggest that manipulation of epitranscriptomic processes influencing translational control may lead to new therapeutic approaches for neurodegenerative diseases.

Antibiotic discovery in the artificial intelligence era

As the global burden of antibiotic resistance continues to grow, creative approaches to antibiotic discovery are needed to accelerate the development of novel medicines. A rapidly progressing computational revolution-artificial intelligence-offers an optimistic path forward due to its ability to alleviate bottlenecks in the antibiotic discovery pipeline. In this review, we discuss how advancements in artificial intelligence are reinvigorating the adoption of past antibiotic discovery models-namely natural product exploration and small molecule screening. We then explore the application of contemporary machine learning approaches to emerging areas of antibiotic discovery, including antibacterial systems biology, drug combination development, antimicrobial peptide discovery, and mechanism of action prediction. Lastly, we propose a call to action for open access of high-quality screening datasets and interdisciplinary collaboration to accelerate the rate at which machine learning models can be trained and new antibiotic drugs can be developed.

Spatial statistics is a comprehensive tool for quantifying cell neighbor relationships and biological processes via tissue image analysis

Automated microscopy and computational image analysis has transformed cell biology, providing quantitative, spatially resolved information on cells and their constituent molecules from the sub-micron to the whole-organ scale. Here we explore the application of spatial statistics to the cellular relationships within tissue microscopy data and discuss how spatial statistics offers cytometry a powerful yet underused mathematical tool set for which the required data are readily captured using standard protocols and microscopy equipment. We also highlight the often-overlooked need to carefully consider the structural heterogeneity of tissues in terms of the applicability of different statistical measures and their accuracy and demonstrate how spatial analyses offer a great deal more than just basic quantification of biological variance. Ultimately, we highlight how statistical modeling can help reveal the hierarchical spatial processes that connect the properties of individual cells to the establishment of biological function.

Combined nanometric and phylogenetic analysis of unique endocytic compartments in Giardia lamblia sheds light on the evolution of endocytosis in Metamonada

Background

Giardia lamblia, a parasitic protist of the Metamonada supergroup, has evolved one of the most diverged endocytic compartment systems investigated so far. Peripheral endocytic compartments, currently known as peripheral vesicles or vacuoles (PVs), perform bulk uptake of fluid phase material which is then digested and sorted either to the cell cytosol or back to the extracellular space.

Results

Here, we present a quantitative morphological characterization of these organelles using volumetric electron microscopy and super-resolution microscopy (SRM). We defined a morphological classification for the heterogenous population of PVs and performed a comparative analysis of PVs and endosome-like organelles in representatives of phylogenetically related taxa, Spironucleus spp. and Tritrichomonas foetus. To investigate the as-yet insufficiently understood connection between PVs and clathrin assemblies in G. lamblia, we further performed an in-depth search for two key elements of the endocytic machinery, clathrin heavy chain (CHC) and clathrin light chain (CLC), across different lineages in Metamonada. Our data point to the loss of a bona fide CLC in the last Fornicata common ancestor (LFCA) with the emergence of a protein analogous to CLC (GlACLC) in the Giardia genus. Finally, the location of clathrin in the various compartments was quantified.

Conclusions

Taken together, this provides the first comprehensive nanometric view of Giardia’s endocytic system architecture and sheds light on the evolution of GlACLC analogues in the Fornicata supergroup and, specific to Giardia, as a possible adaptation to the formation and maintenance of stable clathrin assemblies at PVs.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12915-022-01402-3.

Revealing the Impact of Mitochondrial Fitness During Early Neural Development Using Human Brain Organoids

Mitochondrial homeostasis -including function, morphology, and inter-organelle communication- provides guidance to the intrinsic developmental programs of corticogenesis, while also being responsive to environmental and intercellular signals. Two- and three-dimensional platforms have become useful tools to interrogate the capacity of cells to generate neuronal and glia progeny in a background of metabolic dysregulation, but the mechanistic underpinnings underlying the role of mitochondria during human neurogenesis remain unexplored. Here we provide a concise overview of cortical development and the use of pluripotent stem cell models that have contributed to our understanding of mitochondrial and metabolic regulation of early human brain development. We finally discuss the effects of mitochondrial fitness dysregulation seen under stress conditions such as metabolic dysregulation, absence of developmental apoptosis, and hypoxia; and the avenues of research that can be explored with the use of brain organoids.

Intravital Imaging with Two-Photon Microscopy: A Look into the Kidney

Fluorescence microscopy has represented a crucial technique to explore the cellular and molecular mechanisms in the field of biomedicine. However, the conventional one-photon microscopy exhibits many limitations when living samples are imaged. The new technologies, including two-photon microscopy (2PM), have considerably improved the in vivo study of pathophysiological processes, allowing the investigators to overcome the limits displayed by previous techniques. 2PM enables the real-time intravital imaging of the biological functions in different organs at cellular and subcellular resolution thanks to its improved laser penetration and less phototoxicity. The development of more sensitive detectors and long-wavelength fluorescent dyes as well as the implementation of semi-automatic software for data analysis allowed to gain insights in essential physiological functions, expanding the frontiers of cellular and molecular imaging. The future applications of 2PM are promising to push the intravital microscopy beyond the existing limits. In this review, we provide an overview of the current state-of-the-art methods of intravital microscopy, focusing on the most recent applications of 2PM in kidney physiology.

Recognition of bovine milk somatic cells based on multi-feature extraction and a GBDT-AdaBoost fusion model

Traditional laboratory microscopy for identifying bovine milk somatic cells is subjective, time-consuming, and labor-intensive. The accuracy of the recognition directly through a single classifier is low. In this paper, a novel algorithm that combined the feature extraction algorithm and fusion classification model was proposed to identify the somatic cells. First, 392 cell images from four types of bovine milk somatic cells dataset were trained and tested. Secondly, filtering and the K-means method were used to preprocess and segment the images. Thirdly, the color, morphological, and texture features of the four types of cells were extracted, totaling 100 features. Finally, the gradient boosting decision tree (GBDT)-AdaBoost fusion model was proposed. For the GBDT classifier, the light gradient boosting machine (LightGBM) was used as the weak classifier. The decision tree (DT) was used as the weak classifier of the AdaBoost classifier. The results showed that the average recognition accuracy of the GBDT-AdaBoost reached 98.0%. At the same time, that of random forest (RF), extremely randomized tree (ET), DT, and LightGBM was 79.9, 71.1, 67.3 and 77.2%, respectively. The recall rate of the GBDT-AdaBoost model was the best performance on all types of cells. The F1-Score of the GBDT-AdaBoost model was also better than the results of any single classifiers. The proposed algorithm can effectively recognize the image of bovine milk somatic cells. Moreover, it may provide a reference for recognizing bovine milk somatic cells with similar shape size characteristics and is difficult to distinguish.

Image-Based Monitoring of Cracks: Effectiveness Analysis of an Open-Source Machine Learning-Assisted Procedure

The proper inspection of a cracks pattern over time is a critical diagnosis step to provide a thorough knowledge of the health state of a structure. When monitoring cracks propagating on a planar surface, adopting a single-image-based approach is a more convenient (costly and logistically) solution compared to subjective operators-based solutions. Machine learning (ML)- based monitoring solutions offer the advantage of automation in crack detection; however, complex and time-consuming training must be carried out. This study presents a simple and automated ML-based crack monitoring approach implemented in open sources software that only requires a single image for training. The effectiveness of the approach is assessed conducting work in controlled and real case study sites. For both sites, the generated outputs are significant in terms of accuracy (~1 mm), repeatability (sub-mm) and precision (sub-pixel). The presented results highlight that the successful detection of cracks is achievable with only a straightforward ML-based training procedure conducted on only a single image of the multi-temporal sequence. Furthermore, the use of an innovative camera kit allowed exploiting automated acquisition and transmission fundamental for Internet of Things (IoTs) for structural health monitoring and to reduce user-based operations and increase safety.

BCNet: A Novel Network for Blood Cell Classification

Aims: Most blood diseases, such as chronic anemia, leukemia (commonly known as blood cancer), and hematopoietic dysfunction, are caused by environmental pollution, substandard decoration materials, radiation exposure, and long-term use certain drugs. Thus, it is imperative to classify the blood cell images. Most cell classification is based on the manual feature, machine learning classifier or the deep convolution network neural model. However, manual feature extraction is a very tedious process, and the results are usually unsatisfactory. On the other hand, the deep convolution neural network is usually composed of massive layers, and each layer has many parameters. Therefore, each deep convolution neural network needs a lot of time to get the results. Another problem is that medical data sets are relatively small, which may lead to overfitting problems. Methods: To address these problems, we propose seven models for the automatic classification of blood cells: BCARENet, BCR5RENet, BCMV2RENet, BCRRNet, BCRENet, BCRSNet, and BCNet. The BCNet model is the best model among the seven proposed models. The backbone model in our method is selected as the ResNet-18, which is pre-trained on the ImageNet set. To improve the performance of the proposed model, we replace the last four layers of the trained transferred ResNet-18 model with the three randomized neural networks (RNNs), which are RVFL, ELM, and SNN. The final outputs of our BCNet are generated by the ensemble of the predictions from the three randomized neural networks by the majority voting. We use four multi-classification indexes for the evaluation of our model. Results: The accuracy, average precision, average F1-score, and average recall are 96.78, 97.07, 96.78, and 96.77%, respectively. Conclusion: We offer the comparison of our model with state-of-the-art methods. The results of the proposed BCNet model are much better than other state-of-the-art methods.

Imaging dendritic cell functions

Dendritic cells (DCs) are crucial for the appropriate initiation of adaptive immune responses. During inflammation, DCs capture antigens, mature, and migrate to lymphoid tissues to present foreign material to naïve T cells. These cells get activated and differentiate either into pathogen-specific cytotoxic CD8⁺ T cells that destroy infected cells or into CD4⁺ T helper cells that, among other effector functions, orchestrate antibody production by B cells. DC-mediated antigen presentation is equally important in non-inflammatory conditions. Here, DCs mediate induction of tolerance by presenting self-antigens or harmless environmental antigens and induce differentiation of regulatory T cells or inactivation of self-reactive immune cells. Detailed insights into the biology of DCs are, therefore, crucial for the development of novel vaccines as well as the prevention of autoimmune diseases. As in many other life science areas, our understanding of DC biology would be extremely restricted without bioimaging, a compilation of methods that visualize biological processes. Spatiotemporal tracking of DCs relies on various imaging tools, which not only enable insights into their positioning and migration within tissues or entire organs but also allow visualization of subcellular and molecular processes. This review aims to provide an overview of the imaging toolbox and to provide examples of diverse imaging techniques used to obtain fundamental insights into DC biology.

Brain Immunoinformatics: A Symmetrical Link between Informatics, Wet Lab and the Clinic

Breakthrough advances in informatics over the last decade have thoroughly influenced the field of immunology. The intermingling of machine learning with wet lab applications and clinical results has hatched the newly defined immunoinformatics society. Immunoinformatics of the central neural system, referred to as neuroimmunoinformatics (NII), investigates symmetrical and asymmetrical interactions of the brain-immune interface. This interdisciplinary overview on NII is addressed to bioscientists and computer scientists. We delineate the dominating trajectories and field-shaping achievements and elaborate on future directions using bridging language and terminology. Computation, varying from linear modeling to complex deep learning approaches, fuels neuroimmunology through three core directions. Firstly, by providing big-data analysis software for high-throughput methods such as next-generation sequencing and genome-wide association studies. Secondly, by designing models for the prediction of protein morphology, functions, and symmetrical and asymmetrical protein–protein interactions. Finally, NII boosts the output of quantitative pathology by enabling the automatization of tedious processes such as cell counting, tracing, and arbor analysis. The new classification of microglia, the brain’s innate immune cells, was an NII achievement. Deep sequencing classifies microglia in “sensotypes” to accurately describe the versatility of immune responses to physiological and pathological challenges, as well as to experimental conditions such as xenografting and organoids. NII approaches complex tasks in the brain-immune interface, recognizes patterns and allows for hypothesis-free predictions with ultimate targeted individualized treatment strategies, and personalizes disease prognosis and treatment response.

Visualization and quantitative analyses for mouse embryonic stem cell tracking by manipulating hierarchical data structures using time-lapse confocal microscopy images

We present a cell tracking method for time-lapse confocal microscopy (3D) images that uses dynamic hierarchical data structures to assist cell and colony segmentation and tracking. During the segmentation, the cell and colony numbers and their geometric data are recorded for each 3D image set. In tracking, the colony correspondences between neighboring frames of time-lapse 3D images are first computed using the recorded colony centers. Then, cell correspondences in the correspondent colonies are computed using the recorded cell centers. The examples show the proposed cell tracking method can achieve high tracking accuracy for time-lapse 3D images of undifferentiated but self-renewing mouse embryonic stem (mES) cells where the number and mobility of ES cells in a cell colony may change suddenly by a colony merging or splitting, and cell proliferation or death. The geometric data in the hierarchical data structures also help the visualization and quantitation of the cell shapes and mobility.

Computerized fluorescence microscopy of microbial cells

The upgrading of fluorescence microscopy by the introduction of computer technologies has led to the creation of a new methodology, computerized fluorescence microscopy (CFM). CFM improves subjective visualization and combines it with objective quantitative analysis of the microscopic data. CFM has opened up two fundamentally new opportunities for studying microorganisms. The first is the quantitative measurement of the fluorescence parameters of the targeted fluorophores in association with certain structures of individual cells. The second is the expansion of the boundaries of visualization/resolution of intracellular components beyond the "diffraction limit" of light microscopy into the nanometer range. This enables to obtain unique information about the localization and dynamics of intracellular processes at the molecular level. The purpose of this review is to demonstrate the potential of CFM in the study of fundamental aspects of the structural and functional organization of microbial cells. The basics of computer processing and analysis of digital images are briefly described. The fluorescent molecules used in CFM with an emphasis on fluorescent proteins are characterized. The main methods of super-resolution microscopy (nanoscopy) are presented. The capabilities of various CFM methods for exploring microbial cells at the subcellular level are illustrated by the examples of various studies on yeast and bacteria.

Imaging developmental cell cycles

The last decade has seen a major expansion in development of live biosensors, the tools needed to genetically encode them into model organisms, and the microscopic techniques used to visualize them. When combined, these offer us powerful tools with which to make fundamental discoveries about complex biological processes. In this review, we summarize the availability of biosensors to visualize an essential cellular process, the cell cycle, and the techniques for single-cell tracking and quantification of these reporters. We also highlight studies investigating the connection of cellular behavior to the cell cycle, particularly through live imaging, and anticipate exciting discoveries with the combination of these technologies in developmental contexts.

Identifying novel transcript biomarkers for hepatocellular carcinoma (HCC) using RNA-Seq datasets and machine learning

BACKGROUND

Hepatocellular carcinoma (HCC) is one of the leading causes of cancer death in the world owing to limitations in its prognosis. The current prognosis approaches include radiological examination and detection of serum biomarkers, however, both have limited efficiency and are ineffective in early prognosis. Due to such limitations, we propose to use RNA-Seq data for evaluating putative higher accuracy biomarkers at the transcript level that could help in early prognosis.

METHODS

To identify such potential transcript biomarkers, RNA-Seq data for healthy liver and various HCC cell models were subjected to five different machine learning algorithms: random forest, K-nearest neighbor, Naïve Bayes, support vector machine, and neural networks. Various metrics, namely sensitivity, specificity, MCC, informedness, and AUC-ROC (except for support vector machine) were evaluated. The algorithms that produced the highest values for all metrics were chosen to extract the top features that were subjected to recursive feature elimination. Through recursive feature elimination, the least number of features were obtained to differentiate between the healthy and HCC cell models.

RESULTS

From the metrics used, it is demonstrated that the efficiency of the known protein biomarkers for HCC is comparatively lower than complete transcriptomics data. Among the different machine learning algorithms, random forest and support vector machine demonstrated the best performance. Using recursive feature elimination on top features of random forest and support vector machine three transcripts were selected that had an accuracy of 0.97 and kappa of 0.93. Of the three transcripts, two were protein coding (PARP2-202 and SPON2-203) and one was a non-coding transcript (CYREN-211). Lastly, we demonstrated that these three selected transcripts outperformed randomly taken three transcripts (15,000 combinations), hence were not chance findings, and could then be an interesting candidate for new HCC biomarker development.

CONCLUSION

Using RNA-Seq data combined with machine learning approaches can aid in finding novel transcript biomarkers. The three biomarkers identified: PARP2-202, SPON2-203, and CYREN-211, presented the highest accuracy among all other transcripts in differentiating the healthy and HCC cell models. The machine learning pipeline developed in this study can be used for any RNA-Seq dataset to find novel transcript biomarkers. Code: www.github.com/rajinder4489/ML_biomarkers.

Systems Immunology: Revealing Influenza Immunological Imprint

Understanding protective influenza immunity and identifying immune correlates of protection poses a major challenge and requires an appreciation of the immune system in all of its complexity. While adaptive immune responses such as neutralizing antibodies and influenza-specific T lymphocytes are contributing to the control of influenza virus, key factors of long-term protection are not well defined. Using systems immunology, an approach that combines experimental and computational methods, we can capture the systems-level state of protective immunity and reveal the essential pathways that are involved. New approaches and technological developments in systems immunology offer an opportunity to examine roles and interrelationships of clinical, biological, and genetic factors in the control of influenza infection and have the potential to lead to novel discoveries about influenza immunity that are essential for the development of more effective vaccines to prevent future pandemics. Here, we review recent developments in systems immunology that help to reveal key factors mediating protective immunity.

Recurrent neural network ensemble, a new instrument for the prediction of infectious diseases

Infectious diseases afflict human beings since ancient times. We can classify the infectious disease in two principal types: the emerging diseases, that are caused by new pathogens, and the re-emerging diseases, due to a new spread of a known pathogen. Both types can then be subdivided in natural, accidental or intentional spreads. The risk associated to infectious diseases strongly increased in the last decades, especially because of the globalisation, which leads to a denser and more efficient link between nations, involving that a local infectious may easily spread worldwide, such as the SARS-CoV-2 in 2019-2020. The development of new methods to predict the spread of diseases is crucial. However, sometimes the variables are too many that classical algorithms fail in the prediction. Aim of this work is to investigate the use of an ensemble of recurrent neural networks for disease prediction, using real flu's data to train and develop an instrument with the capability to determine the future flues. Two different types of study have been conducted. The first study investigates the influence of the neural network architecture, and it has been performed using 12 seasons to train the model and 3 seasons to test it. The second test aims to investigate the number of seasons needed to have a good prediction for future ones. The results demonstrated that this approach could ensure very high performances also with simple architectures. The ensemble approach allows to have information about the uncertainty of the prediction, allowing also to take countermeasures as a function of that value. In the future, the use of this approach may be applied to many other types of disease.

Machine learning-based classification of mitochondrial morphology in primary neurons and brain

The mitochondrial network continually undergoes events of fission and fusion. Under physiologic conditions, the network is in equilibrium and is characterized by the presence of both elongated and punctate mitochondria. However, this balanced, homeostatic mitochondrial profile can change morphologic distribution in response to various stressors. Therefore, it is imperative to develop a method that robustly measures mitochondrial morphology with high accuracy. Here, we developed a semi-automated image analysis pipeline for the quantitation of mitochondrial morphology for both in vitro and in vivo applications. The image analysis pipeline was generated and validated utilizing images of primary cortical neurons from transgenic mice, allowing genetic ablation of key components of mitochondrial dynamics. This analysis pipeline was further extended to evaluate mitochondrial morphology in vivo through immunolabeling of brain sections as well as serial block-face scanning electron microscopy. These data demonstrate a highly specific and sensitive method that accurately classifies distinct physiological and pathological mitochondrial morphologies. Furthermore, this workflow employs the use of readily available, free open-source software designed for high throughput image processing, segmentation, and analysis that is customizable to various biological models.

SIMON: Open-Source Knowledge Discovery Platform

Data analysis and knowledge discovery has become more and more important in biology and medicine with the increasing complexity of biological datasets, but the necessarily sophisticated programming skills and in-depth understanding of algorithms needed pose barriers to most biologists and clinicians to perform such research. We have developed a modular open-source software, SIMON, to facilitate the application of 180+ state-of-the-art machine-learning algorithms to high-dimensional biomedical data. With an easy-to-use graphical user interface, standardized pipelines, and automated approach for machine learning and other statistical analysis methods, SIMON helps to identify optimal algorithms and provides a resource that empowers non-technical and technical researchers to identify crucial patterns in biomedical data.

Setting Up an Automated Biomanufacturing Laboratory

Laboratory automation is a key enabling technology for genetic engineering that can lead to higher throughput, more efficient and accurate experiments, better data management and analysis, decrease in the DBT (Design, Build, and Test) cycle turnaround, increase of reproducibility, and savings in lab resources. Choosing the correct framework among so many options available in terms of software, hardware, and skills needed to operate them is crucial for the success of any automation project. This chapter explores the multiple aspects to be considered for the solid development of a biofoundry project including available software and hardware tools, resources, strategies, partnerships, and collaborations in the field needed to speed up the translation of research results to solve important society problems.

PCirc: random forest-based plant circRNA identification software

Background

Circular RNA (circRNA) is a novel type of RNA with a closed-loop structure. Increasing numbers of circRNAs are being identified in plants and animals, and recent studies have shown that circRNAs play an important role in gene regulation. Therefore, identifying circRNAs from increasing amounts of RNA-seq data is very important. However, traditional circRNA recognition methods have limitations. In recent years, emerging machine learning techniques have provided a good approach for the identification of circRNAs in animals. However, using these features to identify plant circRNAs is infeasible because the characteristics of plant circRNA sequences are different from those of animal circRNAs. For example, plants are extremely rich in splicing signals and transposable elements, and their sequence conservation in rice, for example is far less than that in mammals. To solve these problems and better identify circRNAs in plants, it is urgent to develop circRNA recognition software using machine learning based on the characteristics of plant circRNAs.

Results

In this study, we built a software program named PCirc using a machine learning method to predict plant circRNAs from RNA-seq data. First, we extracted different features, including open reading frames, numbers of k-mers, and splicing junction sequence coding, from rice circRNA and lncRNA data. Second, we trained a machine learning model by the random forest algorithm with tenfold cross-validation in the training set. Third, we evaluated our classification according to accuracy, precision, and F1 score, and all scores on the model test data were above 0.99. Fourth, we tested our model by other plant tests, and obtained good results, with accuracy scores above 0.8. Finally, we packaged the machine learning model built and the programming script used into a locally run circular RNA prediction software, Pcirc (https://github.com/Lilab-SNNU/Pcirc).

Conclusion

Based on rice circRNA and lncRNA data, a machine learning model for plant circRNA recognition was constructed in this study using random forest algorithm, and the model can also be applied to plant circRNA recognition such as Arabidopsis thaliana and maize. At the same time, after the completion of model construction, the machine learning model constructed and the programming scripts used in this study are packaged into a localized circRNA prediction software Pcirc, which is convenient for plant circRNA researchers to use.

Deep Learning in Mining Biological Data

Recent technological advancements in data acquisition tools allowed life scientists to acquire multimodal data from different biological application domains. Categorized in three broad types (i.e. images, signals, and sequences), these data are huge in amount and complex in nature. Mining such enormous amount of data for pattern recognition is a big challenge and requires sophisticated data-intensive machine learning techniques. Artificial neural network-based learning systems are well known for their pattern recognition capabilities, and lately their deep architectures-known as deep learning (DL)-have been successfully applied to solve many complex pattern recognition problems. To investigate how DL-especially its different architectures-has contributed and been utilized in the mining of biological data pertaining to those three types, a meta-analysis has been performed and the resulting resources have been critically analysed. Focusing on the use of DL to analyse patterns in data from diverse biological domains, this work investigates different DL architectures' applications to these data. This is followed by an exploration of available open access data sources pertaining to the three data types along with popular open-source DL tools applicable to these data. Also, comparative investigations of these tools from qualitative, quantitative, and benchmarking perspectives are provided. Finally, some open research challenges in using DL to mine biological data are outlined and a number of possible future perspectives are put forward.

The Application of Artificial Intelligence in the Genetic Study of Alzheimer's Disease

Alzheimer's disease (AD) is a neurodegenerative disease in which genetic factors contribute approximately 70% of etiological effects. Studies have found many significant genetic and environmental factors, but the pathogenesis of AD is still unclear. With the application of microarray and next-generation sequencing technologies, research using genetic data has shown explosive growth. In addition to conventional statistical methods for the processing of these data, artificial intelligence (AI) technology shows obvious advantages in analyzing such complex projects. This article first briefly reviews the application of AI technology in medicine and the current status of genetic research in AD. Then, a comprehensive review is focused on the application of AI in the genetic research of AD, including the diagnosis and prognosis of AD based on genetic data, the analysis of genetic variation, gene expression profile, gene-gene interaction in AD, and genetic analysis of AD based on a knowledge base. Although many studies have yielded some meaningful results, they are still in a preliminary stage. The main shortcomings include the limitations of the databases, failing to take advantage of AI to conduct a systematic biology analysis of multilevel databases, and lack of a theoretical framework for the analysis results. Finally, we outlook the direction of future development. It is crucial to develop high quality, comprehensive, large sample size, data sharing resources; a multi-level system biology AI analysis strategy is one of the development directions, and computational creativity may play a role in theory model building, verification, and designing new intervention protocols for AD.

Cell Tracking Profiler - a user-driven analysis framework for evaluating 4D live-cell imaging data

Accurate measurements of cell morphology and behaviour are fundamentally important for understanding how disease, molecules and drugs affect cell function in vivo Here, by using muscle stem cell (muSC) responses to injury in zebrafish as our biological paradigm, we established a 'ground truth' for muSC behaviour. This revealed that segmentation and tracking algorithms from commonly used programs are error-prone, leading us to develop a fast semi-automated image analysis pipeline that allows user-defined parameters for segmentation and correction of cell tracking. Cell Tracking Profiler (CTP) is a package that runs two existing programs, HK Means and Phagosight within the Icy image analysis suite, to enable user-managed cell tracking from 3D time-lapse datasets to provide measures of cell shape and movement. We demonstrate how CTP can be used to reveal changes to cell behaviour of muSCs in response to manipulation of the cell cytoskeleton by small-molecule inhibitors. CTP and the associated tools we have developed for analysis of outputs thus provide a powerful framework for analysing complex cell behaviour in vivo from 4D datasets that are not amenable to straightforward analysis.

Live Cell Microscopy of Murine Polyomavirus Subnuclear Replication Centers

During polyomavirus (PyV) infection, host proteins localize to subnuclear domains, termed viral replication centers (VRCs), to mediate viral genome replication. Although the protein composition and spatial organization of VRCs have been described using high-resolution immunofluorescence microscopy, little is known about the temporal dynamics of VRC formation over the course of infection. We used live cell fluorescence microscopy to analyze VRC formation during murine PyV (MuPyV) infection of a mouse fibroblast cell line that constitutively expresses a GFP-tagged replication protein A complex subunit (GFP-RPA32). The RPA complex forms a heterotrimer (RPA70/32/14) that regulates cellular DNA replication and repair and is a known VRC component. We validated previous observations that GFP-RPA32 relocalized to sites of cellular DNA damage in uninfected cells and to VRCs in MuPyV-infected cells. We then used GFP-RPA32 as a marker of VRC formation and expansion during live cell microscopy of infected cells. VRC formation occurred at variable times post-infection, but the rate of VRC expansion was similar between cells. Additionally, we found that the early viral protein, small TAg (ST), was required for VRC expansion but not VRC formation, consistent with the role of ST in promoting efficient vDNA replication. These results demonstrate the dynamic nature of VRCs over the course of infection and establish an approach for analyzing viral replication in live cells.

A NanoFE simulation-based surrogate machine learning model to predict mechanical functionality of protein networks from live confocal imaging

Sub-cellular mechanics plays a crucial role in a variety of biological functions and dysfunctions. Due to the strong structure-function relationship in cytoskeletal protein networks, light can be shed on their mechanical functionality by investigating their structures. Here, we present a data-driven approach employing a combination of confocal live imaging of fluorescent tagged protein networks, in silico mechanical experiments and machine learning to investigate this relationship. Our designed image processing and nanoFE mechanical simulation framework resolves the structure and mechanical behaviour of cytoskeletal networks and the developed gradient boosting surrogate models linking network structure to its functionality. In this study, for the first time, we perform mechanical simulations of Filamentous Temperature Sensitive Z (FtsZ) complex protein networks with realistic network geometry depicting its skeletal functionality inside organelles (here, chloroplasts) of the moss Physcomitrella patens. Training on synthetically produced simulation data enables predicting the mechanical characteristics of FtsZ network purely based on its structural features (R2⩾0.93), therefore allowing to extract structural principles enabling specific mechanical traits of FtsZ, such as load bearing and resistance to buckling failure in case of large network deformation.

Deep learning-enabled analysis reveals distinct neuronal phenotypes induced by aging and cold-shock

BACKGROUND

Access to quantitative information is crucial to obtain a deeper understanding of biological systems. In addition to being low-throughput, traditional image-based analysis is mostly limited to error-prone qualitative or semi-quantitative assessment of phenotypes, particularly for complex subcellular morphologies. The PVD neuron in Caenorhabditis elegans, which is responsible for harsh touch and thermosensation, undergoes structural degeneration as nematodes age characterized by the appearance of dendritic protrusions. Analysis of these neurodegenerative patterns is labor-intensive and limited to qualitative assessment.

RESULTS

In this work, we apply deep learning to perform quantitative image-based analysis of complex neurodegeneration patterns exhibited by the PVD neuron in C. elegans. We apply a convolutional neural network algorithm (Mask R-CNN) to identify neurodegenerative subcellular protrusions that appear after cold-shock or as a result of aging. A multiparametric phenotypic profile captures the unique morphological changes induced by each perturbation. We identify that acute cold-shock-induced neurodegeneration is reversible and depends on rearing temperature and, importantly, that aging and cold-shock induce distinct neuronal beading patterns.

CONCLUSION

The results of this work indicate that implementing deep learning for challenging image segmentation of PVD neurodegeneration enables quantitatively tracking subtle morphological changes in an unbiased manner. This analysis revealed that distinct patterns of morphological alteration are induced by aging and cold-shock, suggesting different mechanisms at play. This approach can be used to identify the molecular components involved in orchestrating neurodegeneration and to characterize the effect of other stressors on PVD degeneration.

Developing and Preliminary Validating an Automatic Cell Classification System for Bone Marrow Smears: a Pilot Study

Bone marrow smear examination is an indispensable diagnostic tool in the evaluation of hematological diseases, but the process of manual differential count is labor extensive. In this study, we developed an automatic system with integrated scanning hardware and machine learning-based software to perform differential cell count on bone marrow smears to assist diagnosis. The initial development of the artificial neural network was based on 3000 marrow smear samples retrospectively archived from Sir Run Run Shaw Hospital affiliated to Zhejiang University School of Medicine between June 2016 and December 2018. The preliminary field validating test of the system was based on 124 marrow smears newly collected from the Second Affiliated Hospital of Harbin Medical University between April 2019 and November 2019. The study was performed in parallel of machine automatic recognition with conventional manual differential count by pathologists using the microscope. We selected representative 600,000 marrow cell images as training set of the algorithm, followed by random captured 30,867 cell images for validation. In validation, the overall accuracy of automatic cell classification was 90.1% (95% CI, 89.8-90.5%). In a preliminary field validating test, the reliability coefficient (ICC) of cell series proportion between the two analysis methods were high (ICC ≥ 0.883, P < 0.0001) and the results by the two analysis methods were consistent for granulocytes and erythrocytes. The system was effective in cell classification and differential cell count on marrow smears. It provides a useful digital tool in the screening and evaluation of various hematological disorders.

Convolutional neural networks to automate the screening of malaria in low-resource countries

Malaria is an infectious disease caused by Plasmodium parasites, transmitted through mosquito bites. Symptoms include fever, headache, and vomiting, and in severe cases, seizures and coma. The World Health Organization reports that there were 228 million cases and 405,000 deaths in 2018, with Africa representing 93% of total cases and 94% of total deaths. Rapid diagnosis and subsequent treatment are the most effective means to mitigate the progression into serious symptoms. However, many fatal cases have been attributed to poor access to healthcare resources for malaria screenings. In these low-resource settings, the use of light microscopy on a thin blood smear with Giemsa stain is used to examine the severity of infection, requiring tedious and manual counting by a trained technician. To address the malaria endemic in Africa and its coexisting socioeconomic constraints, we propose an automated, mobile phone-based screening process that takes advantage of already existing resources. Through the use of convolutional neural networks (CNNs), we utilize a SSD multibox object detection architecture that rapidly processes thin blood smears acquired via light microscopy to isolate images of individual red blood cells with 90.4% average precision. Then we implement a FSRCNN model that upscales 32 × 32 low-resolution images to 128 × 128 high-resolution images with a PSNR of 30.2, compared to a baseline PSNR of 24.2 through traditional bicubic interpolation. Lastly, we utilize a modified VGG16 CNN that classifies red blood cells as either infected or uninfected with an accuracy of 96.5% in a balanced class dataset. These sequential models create a streamlined screening platform, giving the healthcare provider the number of malaria-infected red blood cells in a given sample. Our deep learning platform is efficient enough to operate exclusively on low-tier smartphone hardware, eliminating the need for high-speed internet connection.